{"total":159,"rows":[{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372,"area":null},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138,"area":null},{"id":"2103.16596","title":"Benchmarks for Deep Off-Policy Evaluation","created":"2021-03-30","cited_by_count":89,"area":null},{"id":"2105.12196","title":"From Motor Control to Team Play in Simulated Humanoid Football","created":"2021-05-25","cited_by_count":87,"area":null},{"id":"2104.14795","title":"Mitigating Political Bias in Language Models Through Reinforced Calibration","created":"2021-04-30","cited_by_count":73,"area":null},{"id":"2110.06192","title":"Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes","created":"2021-10-12","cited_by_count":71,"area":null},{"id":"2201.11927","title":"Constrained Variational Policy Optimization for Safe Reinforcement Learning","created":"2022-01-28","cited_by_count":71,"area":null},{"id":"2503.14286","title":"Tapered Off-Policy REINFORCE: Stable and efficient reinforcement learning for LLMs","created":"2025-03-18","cited_by_count":61,"area":null},{"id":"2102.01567","title":"A Lyapunov Theory for Finite-Sample Guarantees of Asynchronous Q-Learning and TD-Learning Variants","created":"2021-02-02","cited_by_count":57,"area":null},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2106.11144","title":"Scientific multi-agent reinforcement learning for wall-models of turbulent flows","created":"2021-06-21","cited_by_count":52,"area":null},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47,"area":null},{"id":"2505.24034","title":"LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Training","created":"2025-05-29","cited_by_count":42,"area":null},{"id":"2312.02027","title":"Stochastic Optimal Control Matching","created":"2023-12-04","cited_by_count":40,"area":null},{"id":"2111.02552","title":"Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies","created":"2021-11-03","cited_by_count":38,"area":null},{"id":"2205.14691","title":"On the Robustness of Safe Reinforcement Learning under Observational Perturbations","created":"2022-05-29","cited_by_count":38,"area":null},{"id":"2205.15043","title":"RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch","created":"2022-05-30","cited_by_count":30,"area":null},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28,"area":null},{"id":"2102.09318","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm","created":"2021-02-18","cited_by_count":26,"area":null},{"id":"2104.13844","title":"A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning","created":"2021-04-28","cited_by_count":26,"area":null},{"id":"2106.10251","title":"Active Offline Policy Selection","created":"2021-06-18","cited_by_count":26,"area":null},{"id":"2107.08966","title":"Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration","created":"2021-07-19","cited_by_count":25,"area":null},{"id":"2105.12540","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic with Linear Function Approximation","created":"2021-05-26","cited_by_count":22,"area":null},{"id":"2102.13515","title":"Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning","created":"2021-02-24","cited_by_count":21,"area":null},{"id":"2211.07819","title":"General Intelligence Requires Rethinking Exploration","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2406.11741","title":"Transcendence: Generative Models Can Outperform The Experts That Train Them","created":"2024-06-17","cited_by_count":20,"area":null},{"id":"2103.00107","title":"Revisiting Peng's Q($\\lambda$) for Modern Reinforcement Learning","created":"2021-02-27","cited_by_count":19,"area":null},{"id":"2103.07084","title":"Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Information","created":"2021-03-12","cited_by_count":19,"area":null},{"id":"2106.06854","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","created":"2021-06-12","cited_by_count":19,"area":null},{"id":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2106.12729","title":"Finite-Sample Analysis of Off-Policy TD-Learning via Generalized Bellman Operators","created":"2021-06-24","cited_by_count":17,"area":null},{"id":"2305.00477","title":"Posterior Sampling for Deep Reinforcement Learning","created":"2023-04-30","cited_by_count":16,"area":null},{"id":"2103.17258","title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning","created":"2021-03-31","cited_by_count":15,"area":null},{"id":"2104.06521","title":"TAAC: Temporally Abstract Actor-Critic for Continuous Control","created":"2021-04-13","cited_by_count":15,"area":null},{"id":"2110.03363","title":"Evaluating model-based planning and planner amortization for continuous control","created":"2021-10-07","cited_by_count":15,"area":null},{"id":"2401.00364","title":"Tight Finite Time Bounds of Two-Time-Scale Linear Stochastic Approximation with Markovian Noise","created":"2023-12-31","cited_by_count":15,"area":null},{"id":"2106.14979","title":"On component interactions in two-stage recommender systems","created":"2021-06-28","cited_by_count":14,"area":null},{"id":"2301.13734","title":"Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design","created":"2023-01-31","cited_by_count":14,"area":null},{"id":"2305.05239","title":"Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection","created":"2023-05-09","cited_by_count":14,"area":null},{"id":"2310.10735","title":"Building Persona Consistent Dialogue Agents with Offline Reinforcement Learning","created":"2023-10-16","cited_by_count":14,"area":null},{"id":"2105.14900","title":"A unified view of likelihood ratio and reparameterization gradients","created":"2021-05-31","cited_by_count":12,"area":null},{"id":"2112.04145","title":"A Review for Deep Reinforcement Learning in Atari:Benchmarks, Challenges, and Solutions","created":"2021-12-08","cited_by_count":12,"area":null},{"id":"2204.03084","title":"Knowledge Infused Decoding","created":"2022-04-06","cited_by_count":12,"area":null},{"id":"2205.10047","title":"The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure","created":"2022-05-20","cited_by_count":12,"area":null},{"id":"2109.06093","title":"Direct Advantage Estimation","created":"2021-09-13","cited_by_count":11,"area":null},{"id":"2306.10171","title":"Bootstrapped Representations in Reinforcement Learning","created":"2023-06-16","cited_by_count":11,"area":null},{"id":"2102.01985","title":"Variance Penalized On-Policy and Off-Policy Actor-Critic","created":"2021-02-03","cited_by_count":10,"area":null},{"id":"2107.01715","title":"Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction","created":"2021-07-04","cited_by_count":10,"area":null},{"id":"2207.07570","title":"The Nature of Temporal Difference Errors in Multi-step Distributional Reinforcement Learning","created":"2022-07-15","cited_by_count":10,"area":null},{"id":"2209.14940","title":"Reinforcement Learning Algorithms: An Overview and Classification","created":"2022-09-29","cited_by_count":10,"area":null},{"id":"2302.09339","title":"Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization","created":"2023-02-18","cited_by_count":10,"area":null},{"id":"2303.04096","title":"Mastering Strategy Card Game (Legends of Code and Magic) via End-to-End Policy and Optimistic Smooth Fictitious Play","created":"2023-03-07","cited_by_count":10,"area":null},{"id":"2103.05147","title":"Model-free Policy Learning with Reward Gradients","created":"2021-03-09","cited_by_count":9,"area":null},{"id":"2203.00715","title":"Learning Robust Real-Time Cultural Transmission without Human Data","created":"2022-03-01","cited_by_count":9,"area":null},{"id":"2604.08706","title":"Efficient RL Training for LLMs with Experience Replay","created":"2026-04-09","cited_by_count":9,"area":null},{"id":"2104.07219","title":"Multitasking Inhibits Semantic Drift","created":"2021-04-15","cited_by_count":8,"area":null},{"id":"2105.12991","title":"Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization","created":"2021-05-27","cited_by_count":8,"area":null},{"id":"2106.15419","title":"Convergent and Efficient Deep Q Network Algorithm","created":"2021-06-29","cited_by_count":8,"area":null},{"id":"2111.03474","title":"Supervised Advantage Actor-Critic for Recommender Systems","created":"2021-11-05","cited_by_count":8,"area":null},{"id":"2106.00707","title":"An Entropy Regularization Free Mechanism for Policy-based Reinforcement Learning","created":"2021-06-01","cited_by_count":7,"area":null},{"id":"2106.06232","title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","created":"2021-06-11","cited_by_count":7,"area":null},{"id":"2108.08485","title":"Language Model Augmented Relevance Score","created":"2021-08-19","cited_by_count":7,"area":null},{"id":"2110.12840","title":"Self-Consistent Models and Values","created":"2021-10-25","cited_by_count":7,"area":null},{"id":"2111.12673","title":"Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning","created":"2021-11-24","cited_by_count":6,"area":null},{"id":"2112.04153","title":"Model-Value Inconsistency as a Signal for Epistemic Uncertainty","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2206.13901","title":"Value Function Decomposition for Iterative Design of Reinforcement Learning Agents","created":"2022-06-24","cited_by_count":6,"area":null},{"id":"2208.12328","title":"Autonomous Unmanned Aerial Vehicle Navigation using Reinforcement Learning: A Systematic Review","created":"2022-08-25","cited_by_count":6,"area":null},{"id":"2209.15166","title":"Reward Shaping for User Satisfaction in a REINFORCE Recommender","created":"2022-09-30","cited_by_count":6,"area":null},{"id":"2301.11321","title":"Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning","created":"2023-01-26","cited_by_count":6,"area":null},{"id":"2302.12120","title":"Sequential Counterfactual Risk Minimization","created":"2023-02-23","cited_by_count":6,"area":null},{"id":"2303.03955","title":"Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning","created":"2023-03-07","cited_by_count":6,"area":null},{"id":"2106.13125","title":"Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation","created":"2021-06-24","cited_by_count":5,"area":null},{"id":"2111.03936","title":"SOPE: Spectrum of Off-Policy Estimators","created":"2021-11-06","cited_by_count":5,"area":null},{"id":"2210.03325","title":"Elastic Step DQN: A novel multi-step algorithm to alleviate overestimation in Deep QNetworks","created":"2022-10-07","cited_by_count":5,"area":null},{"id":"2302.09212","title":"HOPE: Human-Centric Off-Policy Evaluation for E-Learning and Healthcare","created":"2023-02-18","cited_by_count":5,"area":null},{"id":"2306.07552","title":"Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second","created":"2023-06-13","cited_by_count":5,"area":null},{"id":"2102.06782","title":"Q-Value Weighted Regression: Reinforcement Learning with Limited Data","created":"2021-02-12","cited_by_count":4,"area":null},{"id":"2102.12962","title":"Bias-reduced Multi-step Hindsight Experience Replay for Efficient Multi-goal Reinforcement Learning","created":"2021-02-25","cited_by_count":4,"area":null},{"id":"2209.12347","title":"Opportunities and Challenges from Using Animal Videos in Reinforcement Learning for Navigation","created":"2022-09-25","cited_by_count":4,"area":null},{"id":"2305.03608","title":"On the Optimality, Stability, and Feasibility of Control Barrier Functions: An Adaptive Learning-Based Approach","created":"2023-05-05","cited_by_count":4,"area":null},{"id":"2306.15625","title":"Value-aware Importance Weighting for Off-policy Reinforcement Learning","created":"2023-06-27","cited_by_count":4,"area":null},{"id":"2401.05133","title":"Neural Population Learning beyond Symmetric Zero-sum Games","created":"2024-01-10","cited_by_count":4,"area":null},{"id":"2107.01360","title":"Supervised Off-Policy Ranking","created":"2021-07-03","cited_by_count":3,"area":null},{"id":"2201.06468","title":"Chaining Value Functions for Off-Policy Learning","created":"2022-01-17","cited_by_count":3,"area":null},{"id":"2201.08115","title":"Priors, Hierarchy, and Information Asymmetry for Skill Transfer in Reinforcement Learning","created":"2022-01-20","cited_by_count":3,"area":null},{"id":"2208.00755","title":"Mitigating Off-Policy Bias in Actor-Critic Methods with One-Step Q-learning: A Novel Correction Approach","created":"2022-08-01","cited_by_count":3,"area":null},{"id":"2208.03247","title":"An Approximate Policy Iteration Viewpoint of Actor-Critic Algorithms","created":"2022-08-05","cited_by_count":3,"area":null},{"id":"2212.07611","title":"Residual Policy Learning for Powertrain Control","created":"2022-12-15","cited_by_count":3,"area":null},{"id":"2303.06389","title":"Uncertainty-Aware Instance Reweighting for Off-Policy Learning","created":"2023-03-11","cited_by_count":3,"area":null},{"id":"2312.11551","title":"Probabilistic Offline Policy Ranking with Approximate Bayesian Computation","created":"2023-12-17","cited_by_count":3,"area":null},{"id":"2505.11081","title":"ShiQ: Bringing back Bellman to LLMs","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2606.03070","title":"ASymPO: Asymmetric-Scale Policy Optimization for Asynchronous LLM Post-Training Without Behavior Information","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2106.00922","title":"An Empirical Comparison of Off-policy Prediction Learning Algorithms on the Collision Task","created":"2021-06-02","cited_by_count":2,"area":null},{"id":"2106.10566","title":"Scalable Safety-Critical Policy Evaluation with Accelerated Rare Event Sampling","created":"2021-06-19","cited_by_count":2,"area":null},{"id":"2109.10736","title":"Estimation Error Correction in Deep Reinforcement Learning for Deterministic Actor-Critic Methods","created":"2021-09-22","cited_by_count":2,"area":null},{"id":"2111.11229","title":"Off-Policy Correction For Multi-Agent Reinforcement Learning","created":"2021-11-22","cited_by_count":2,"area":null},{"id":"2203.13319","title":"Remember and Forget Experience Replay for Multi-Agent Reinforcement Learning","created":"2022-03-24","cited_by_count":2,"area":null},{"id":"2205.10044","title":"Towards biologically plausible Dreaming and Planning in recurrent spiking networks","created":"2022-05-20","cited_by_count":2,"area":null},{"id":"2207.13453","title":"Safe and Robust Experience Sharing for Deterministic Policy Gradient Algorithms","created":"2022-07-27","cited_by_count":2,"area":null},{"id":"2212.04136","title":"Design and Planning of Flexible Mobile Micro-Grids Using Deep Reinforcement Learning","created":"2022-12-08","cited_by_count":2,"area":null}],"next_cursor":"100"}